The auto-skill-loader MCP server allows AI agents to automatically load a library of skills at session start, eliminating the need for explicit triggers or fuzzy matching.
From the registry: Auto-loads skills into agent sessions. MiniMax vision and search proxy.
Please install the `auto-skill-loader` MCP server into my current AI client (that's you).
Optional prerequisites:
- Create skills directory + config — Create ~/.config/auto-skill-loader/ and populate config.yaml with active_skills and skills_dir.
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["auto-skill-loader"]
- optional environment variables:
- `MINIMAX_TOKEN_PLAN_KEY`: MiniMax Token Plan API key, only needed if using the bundled minimax vision/web-search proxy tools (example: `<your-minimax-api-key>`)
Note: uvx path is the recommended zero-install option. Python pip install is an alternative.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MINIMAX_TOKEN_PLAN_KEYrequiredAPI key for accessing MiniMax servicesAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.